基于神经网络的助力搬运装置自适应控制方法研究
|
摘要
为提高助力搬运装置在建筑工地等复杂路况下的适用性,通过对国内外助力系统及其控制方法发展现状的调查和分析,提出一种智能助力控制系统。首先建立控制模型,在智能控制的研究中发现BP神经网络能够对输入信息进行识别并分类处理,且计算较简单,容易实现,但BP神经网络隐含层节点数难以确定、易陷入局部最小值,因此,采用遗传算法对BP神经网络进行优化(GA-BP),并设计具体实现方法。采集平坦、斜坡两种路况的数据,通过人工赋予理想输出数据,将其一部分作为训练数据,对GA-BP神经网络及BP神经网络进行对比训练,另一部分作为验证数据,检验两种网络的训练结果。使用MATLAB进行数据仿真分析,验证GA-BP神经网络控制方法的可行性。试验结果表明:这种控制方法能够有效地解决助力搬运装置在复杂路况下的自适应控制问题。
In order to improve the applicability of the power handling equipment in the construction site and other complex road conditions,through the investigation and analysis on the development status of the power system and its control methods at home and abroad,an intelligent power control system was presented. The intelligent control model was established. Through the research on intelligent control of BP,it was found in the neural network could be used to identify and classify the input information,and the calculation was simple,easy to implement,but the lack of BP neural network was difficult to determine the number of hidden layer nodes,easy to fall into the local minimum. Therefore,the genetic algorithm was used to optimize BP neural network( GA-BP),and the concrete implementation method was designed. Collecting two kinds of condition data on flat and slope,ideal output data was given by artificial,the division were as the training data,GA-BP neural network and BP neural network were compared to train,the other were as the validation data,two kinds of network training results were tested. MATLAB was used for data simulation experiments to verify the feasibility of GA-BP neural network control method. The experimental results show that this control method can be used to effectively solve the adaptive control problem of the power handling device in complex road conditions.
In order to improve the applicability of the power handling equipment in the construction site and other complex road conditions,through the investigation and analysis on the development status of the power system and its control methods at home and abroad,an intelligent power control system was presented. The intelligent control model was established. Through the research on intelligent control of BP,it was found in the neural network could be used to identify and classify the input information,and the calculation was simple,easy to implement,but the lack of BP neural network was difficult to determine the number of hidden layer nodes,easy to fall into the local minimum. Therefore,the genetic algorithm was used to optimize BP neural network( GA-BP),and the concrete implementation method was designed. Collecting two kinds of condition data on flat and slope,ideal output data was given by artificial,the division were as the training data,GA-BP neural network and BP neural network were compared to train,the other were as the validation data,two kinds of network training results were tested. MATLAB was used for data simulation experiments to verify the feasibility of GA-BP neural network control method. The experimental results show that this control method can be used to effectively solve the adaptive control problem of the power handling device in complex road conditions.
引文
[1]伊茹梦.人工神经网络理论与应用[J].科技经济刊,2015(18):59-60.
[2]张雷,刘希玉.对传过程神经元网络及其应用研究[J].微型机与应用,2012(17):67-68.ZHANG L,LIU X Y. Counterpropagation Process Neural Network and Its Application[J]. Microcomputer&Its Applications,2012(17):67-68.
[3]黄丽. BP神经网络算法改进及应用研究[D].重庆:重庆师范大学,2008.
[4]张松兰.基于改进遗传算法的神经网络控制[J].火力与指挥控制,2012(6):170-172.ZHANG S L. Study on Neural Network Control Based on Improved Genetic Algorithm[J]. Fire Control&Command Control,2012(6):170-172.
[5]刘春艳,凌建春,寇林元,等. GA-BP神经网络与BP神经网络性能比较[J].中国卫生统计,2013,30(2):173-176.LIU C Y,LING J C,KOU L Y,et al. Performance Comparison between GA-BP Neural Network and BP Neural Network[J]. Chinese Journal of Health Statistics,2013,30(2):173-176.
[6]章鹏,杨冬,高智伟,等.基于STM32的力跟随电动助力推车控制系统设计[J].仪表技术与传感器,2016(1):59-62.ZHANG P,YANG D,GAO Z W,et al. Design of Control System in Force Tracking Electric Power Trolley Based on STM32[J]. Instrument Technique and Sensor,2016(1):59-62.
[7]SAMANTA B,AL-BALUSHI K R,AL-ARAIMI S A. Artificial Neural Networks and Genetic Algorithms for Gear Fault Detection[J]. Mechanical Systems&Signal Processing,2004,18(5):1273-1282.
[8]陈永建,周艳.遗传算法编码方式的应用及其改进算法的研究[J].太原师范学院学报(自然科学版),2008,7(2):76-78.CHEN Y J,ZHOU Y. Application of Coding Genetic Algorithm and its Improvement Research[J]. Journal of Taiyuan Normal University(Natural Science Edition),2008,7(2):76-78.
[9]焦斌,叶明星. BP神经网络隐层单元数确定方法[J].上海电机学院学报,2013(3):113-116.JIAO B,YE M X. Determination of Hidden Unit Number in a BP Neural Network[J]. Journal of Shanghai Dianji University,2013(3):113-116.
[10]丁硕,巫庆辉.基于改进BP神经网络的函数逼近性能对比研究[J].计算机与现代化,2012(11):10-13.DING S,WU Q H. Performance Comparison of Function Approximation Based on Improved BP Neural Network[J]. Computer and Modernization,2012(11):10-13.
[2]张雷,刘希玉.对传过程神经元网络及其应用研究[J].微型机与应用,2012(17):67-68.ZHANG L,LIU X Y. Counterpropagation Process Neural Network and Its Application[J]. Microcomputer&Its Applications,2012(17):67-68.
[3]黄丽. BP神经网络算法改进及应用研究[D].重庆:重庆师范大学,2008.
[4]张松兰.基于改进遗传算法的神经网络控制[J].火力与指挥控制,2012(6):170-172.ZHANG S L. Study on Neural Network Control Based on Improved Genetic Algorithm[J]. Fire Control&Command Control,2012(6):170-172.
[5]刘春艳,凌建春,寇林元,等. GA-BP神经网络与BP神经网络性能比较[J].中国卫生统计,2013,30(2):173-176.LIU C Y,LING J C,KOU L Y,et al. Performance Comparison between GA-BP Neural Network and BP Neural Network[J]. Chinese Journal of Health Statistics,2013,30(2):173-176.
[6]章鹏,杨冬,高智伟,等.基于STM32的力跟随电动助力推车控制系统设计[J].仪表技术与传感器,2016(1):59-62.ZHANG P,YANG D,GAO Z W,et al. Design of Control System in Force Tracking Electric Power Trolley Based on STM32[J]. Instrument Technique and Sensor,2016(1):59-62.
[7]SAMANTA B,AL-BALUSHI K R,AL-ARAIMI S A. Artificial Neural Networks and Genetic Algorithms for Gear Fault Detection[J]. Mechanical Systems&Signal Processing,2004,18(5):1273-1282.
[8]陈永建,周艳.遗传算法编码方式的应用及其改进算法的研究[J].太原师范学院学报(自然科学版),2008,7(2):76-78.CHEN Y J,ZHOU Y. Application of Coding Genetic Algorithm and its Improvement Research[J]. Journal of Taiyuan Normal University(Natural Science Edition),2008,7(2):76-78.
[9]焦斌,叶明星. BP神经网络隐层单元数确定方法[J].上海电机学院学报,2013(3):113-116.JIAO B,YE M X. Determination of Hidden Unit Number in a BP Neural Network[J]. Journal of Shanghai Dianji University,2013(3):113-116.
[10]丁硕,巫庆辉.基于改进BP神经网络的函数逼近性能对比研究[J].计算机与现代化,2012(11):10-13.DING S,WU Q H. Performance Comparison of Function Approximation Based on Improved BP Neural Network[J]. Computer and Modernization,2012(11):10-13.